Learning with Deep Cascades


We introduce a broad learning model formed by cascades of predictors, Deep Cascades, that is structured as general decision trees in which leaf predictors or node questions may be members of rich function families. We present new detailed data-dependent theoretical guarantees for learning with Deep Cascades with complex leaf predictors or node question in terms of the Rademacher complexities of the sub-families composing these sets of predictors and the fraction of sample points correctly classified at each leaf. These general guarantees can guide the design of a variety of different algorithms for deep cascade models and we give a detailed description of two such algorithms. Our second algorithm uses as node and leaf classifiers SVM predictors and we report the results of experiments comparing its performance with that of SVM combined with polynomial kernels.